[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PATCH COLO-Frame v19 14/22] COLO: Implement the process of
From: |
zhanghailiang |
Subject: |
[Qemu-devel] [PATCH COLO-Frame v19 14/22] COLO: Implement the process of failover for primary VM |
Date: |
Thu, 1 Sep 2016 11:24:17 +0800 |
For primary side, if COLO gets failover request from users.
To be exact, gets 'x_colo_lost_heartbeat' command.
COLO thread will exit the loop while the failover BH does the
cleanup work and resumes VM.
Signed-off-by: zhanghailiang <address@hidden>
Signed-off-by: Li Zhijian <address@hidden>
Reviewed-by: Dr. David Alan Gilbert <address@hidden>
---
v13:
- Add Reviewed-by tag
v12:
- Fix error report and remove unnecessary check in
primary_vm_do_failover() (Dave's suggestion)
v11:
- Don't call migration_end() in primary_vm_do_failover(),
The cleanup work will be done in migration_thread().
- Remove vm_start() in primary_vm_do_failover() which also been
done in migraiton_thread()
v10:
- Call migration_end() in primary_vm_do_failover()
---
include/migration/colo.h | 3 +++
include/migration/failover.h | 1 +
migration/colo-failover.c | 7 +++++-
migration/colo.c | 54 ++++++++++++++++++++++++++++++++++++++++++--
4 files changed, 62 insertions(+), 3 deletions(-)
diff --git a/include/migration/colo.h b/include/migration/colo.h
index e9ac2c3..e32eef4 100644
--- a/include/migration/colo.h
+++ b/include/migration/colo.h
@@ -32,4 +32,7 @@ void *colo_process_incoming_thread(void *opaque);
bool migration_incoming_in_colo_state(void);
COLOMode get_colo_mode(void);
+
+/* failover */
+void colo_do_failover(MigrationState *s);
#endif
diff --git a/include/migration/failover.h b/include/migration/failover.h
index fe71bb4..c4bd81e 100644
--- a/include/migration/failover.h
+++ b/include/migration/failover.h
@@ -26,5 +26,6 @@ void failover_init_state(void);
int failover_set_state(int old_state, int new_state);
int failover_get_state(void);
void failover_request_active(Error **errp);
+bool failover_request_is_active(void);
#endif
diff --git a/migration/colo-failover.c b/migration/colo-failover.c
index 82196b2..607a294 100644
--- a/migration/colo-failover.c
+++ b/migration/colo-failover.c
@@ -33,7 +33,7 @@ static void colo_failover_bh(void *opaque)
error_report("Unknown error for failover, old_state = %d", old_state);
return;
}
- /* TODO: Do failover work */
+ colo_do_failover(NULL);
}
void failover_request_active(Error **errp)
@@ -68,6 +68,11 @@ int failover_get_state(void)
return atomic_read(&failover_state);
}
+bool failover_request_is_active(void)
+{
+ return failover_get_state() != FAILOVER_STATUS_NONE;
+}
+
void qmp_x_colo_lost_heartbeat(Error **errp)
{
if (get_colo_mode() == COLO_MODE_UNKNOWN) {
diff --git a/migration/colo.c b/migration/colo.c
index b94972c..8d6f585 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -41,6 +41,40 @@ bool migration_incoming_in_colo_state(void)
return mis && (mis->state == MIGRATION_STATUS_COLO);
}
+static bool colo_runstate_is_stopped(void)
+{
+ return runstate_check(RUN_STATE_COLO) || !runstate_is_running();
+}
+
+static void primary_vm_do_failover(void)
+{
+ MigrationState *s = migrate_get_current();
+ int old_state;
+
+ migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
+ MIGRATION_STATUS_COMPLETED);
+
+ old_state = failover_set_state(FAILOVER_STATUS_HANDLING,
+ FAILOVER_STATUS_COMPLETED);
+ if (old_state != FAILOVER_STATUS_HANDLING) {
+ error_report("Incorrect state (%d) while doing failover for Primary
VM",
+ old_state);
+ return;
+ }
+}
+
+void colo_do_failover(MigrationState *s)
+{
+ /* Make sure VM stopped while failover happened. */
+ if (!colo_runstate_is_stopped()) {
+ vm_stop_force_state(RUN_STATE_COLO);
+ }
+
+ if (get_colo_mode() == COLO_MODE_PRIMARY) {
+ primary_vm_do_failover();
+ }
+}
+
static void colo_send_message(QEMUFile *f, COLOMessage msg,
Error **errp)
{
@@ -162,9 +196,20 @@ static int colo_do_checkpoint_transaction(MigrationState
*s,
bioc->usage = 0;
qemu_mutex_lock_iothread();
+ if (failover_request_is_active()) {
+ qemu_mutex_unlock_iothread();
+ goto out;
+ }
vm_stop_force_state(RUN_STATE_COLO);
qemu_mutex_unlock_iothread();
trace_colo_vm_state_change("run", "stop");
+ /*
+ * Failover request bh could be called after vm_stop_force_state(),
+ * So we need check failover_request_is_active() again.
+ */
+ if (failover_request_is_active()) {
+ goto out;
+ }
/* Disable block migration */
s->params.blk = 0;
@@ -259,6 +304,11 @@ static void colo_process_checkpoint(MigrationState *s)
trace_colo_vm_state_change("stop", "run");
while (s->state == MIGRATION_STATUS_COLO) {
+ if (failover_request_is_active()) {
+ error_report("failover request");
+ goto out;
+ }
+
current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
if (current_time - checkpoint_time <
s->parameters.x_checkpoint_delay) {
@@ -280,9 +330,9 @@ out:
if (local_err) {
error_report_err(local_err);
}
- migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
- MIGRATION_STATUS_COMPLETED);
+
qemu_fclose(fb);
+
if (s->rp_state.from_dst_file) {
qemu_fclose(s->rp_state.from_dst_file);
}
--
1.8.3.1
- [Qemu-devel] [PATCH COLO-Frame v19 00/22] COarse-grain LOck-stepping(COLO) Virtual Machines for Non-stop Service (FT), zhanghailiang, 2016/08/31
- [Qemu-devel] [PATCH COLO-Frame v19 02/22] COLO: migrate COLO related info to secondary node, zhanghailiang, 2016/08/31
- [Qemu-devel] [PATCH COLO-Frame v19 05/22] COLO: Establish a new communicating path for COLO, zhanghailiang, 2016/08/31
- [Qemu-devel] [PATCH COLO-Frame v19 04/22] migration: Switch to COLO process after finishing loadvm, zhanghailiang, 2016/08/31
- [Qemu-devel] [PATCH COLO-Frame v19 07/22] COLO: Add a new RunState RUN_STATE_COLO, zhanghailiang, 2016/08/31
- [Qemu-devel] [PATCH COLO-Frame v19 14/22] COLO: Implement the process of failover for primary VM,
zhanghailiang <=
- [Qemu-devel] [PATCH COLO-Frame v19 13/22] COLO: Introduce state to record failover process, zhanghailiang, 2016/08/31
- [Qemu-devel] [PATCH COLO-Frame v19 10/22] COLO: Add checkpoint-delay parameter for migrate-set-parameters, zhanghailiang, 2016/08/31
- [Qemu-devel] [PATCH COLO-Frame v19 12/22] COLO: Add 'x-colo-lost-heartbeat' command to trigger failover, zhanghailiang, 2016/08/31
- [Qemu-devel] [PATCH COLO-Frame v19 19/22] COLO: Update the global runstate after going into colo state, zhanghailiang, 2016/08/31
- [Qemu-devel] [PATCH COLO-Frame v19 18/22] COLO: Handle shutdown command for VM in COLO state, zhanghailiang, 2016/08/31
- [Qemu-devel] [PATCH COLO-Frame v19 15/22] COLO: Implement failover work for secondary VM, zhanghailiang, 2016/08/31
- [Qemu-devel] [PATCH COLO-Frame v19 22/22] configure: Support enable/disable COLO feature, zhanghailiang, 2016/08/31
- [Qemu-devel] [PATCH COLO-Frame v19 21/22] docs: Add documentation for COLO feature, zhanghailiang, 2016/08/31
- [Qemu-devel] [PATCH COLO-Frame v19 16/22] COLO: Shutdown related socket fd while do failover, zhanghailiang, 2016/08/31
- [Qemu-devel] [PATCH COLO-Frame v19 17/22] COLO: Don't do failover while loading VM's state, zhanghailiang, 2016/08/31